Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive behaviour beyond them: aggregates only with no seller or buyer identity, and below min_sample the result is published: false with every figure null. It also discloses that it works without credentials, which is operationally important for an agent deciding whether it can call it early in a flow.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries information and the scoping qualifiers are front-loaded, so there is little waste. The opening sentence is a long run-on that packs the entire output contract into one breath, which hurts scanability, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on the burden of describing return fields and the null/published:false case, which it does thoroughly. It leaves the response envelope (nesting, whether figures are nested under a currency key) and the actual min_sample threshold unstated, so it is thorough but not fully complete for a six-parameter analytics call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning: it explains which output fields are affected by rail (intent-cleared vs listing-bought) and clearing_rule (best bid vs second price), and pins the output format of clearing_price as minor-unit strings. Minor gap: min_sample is referenced as behavioural threshold but is not a parameter, which could momentarily confuse an agent looking for it in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Price a job from data' — and immediately enumerates the metrics returned (clearing_price p10/p50/p90, median_minutes_to_delivery, first_pass_accept_bp, dispute_rate_bp, outcome_mix, funding_mix, fill_rate_bp), which is far more precise than any sibling. It does not, however, name or contrast itself with the closest sibling analytics tools (catalog_describe_category, procurement_memory_get), so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use guidance by naming the downstream siblings it feeds: 'Use it to set an intents_post budget_ceiling_pence or an intents_bid amount.' That is real routing information rather than vague context. It stops short of stating when NOT to use it or what to do instead if the tool returns published: false, so it is clear context without explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.